INDEX

Explanations

references to needles and their use or impact in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enor

-0.18

stru

-0.16

aines

-0.15

Lens

-0.14

akh

-0.14

ellen

-0.14

vla

-0.14

¥¤

-0.14

utsch

-0.13

ÙħØ©

-0.13

POSITIVE LOGITS

 poil

0.17

lopen

0.16

!--

0.15

azzo

0.14

brown

0.14

 needles

0.14

posables

0.14

itter

0.14

inct

0.14

stick

0.14

Activations Density 0.014%

references to needles and their use or impact in various contexts

No Comments

No Known Activations